Algorithm Primer Series 1:k-means

K-means is an unsupervised learning algorithm for clustering.

(from http://www.cnblogs.com/jerrylead/archive/2011/04/06/2006910.html) shows the clustering process when the K-means algorithm k=2.

The first step: given the K center point, and then loop through all the data points, calculate the distance from each data point to the K center point, the shortest distance is attributed to the center point

Step two: Use the results in the first step to recalculate the center point

The third step: the first second step of the loop until the K center point no longer changes.

Algorithm Primer Series 1:k-means